Skip to content

Replace concat_elements_utf8_many BufferBuilders with Vec #10633

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
cakeni wants to merge 1 commit into
base: main
Choose a base branch
from
+7 −7
Open

Replace concat_elements_utf8_many BufferBuilders with Vec #10633

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 7 additions & 7 deletions arrow-string/src/concat_elements.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,32 +138,32 @@ pub fn concat_elements_utf8_many<Offset: OffsetSizeTrait>(
.map(|a| a.value_offsets().iter().peekable())
.collect::<Vec<_>>();

let mut output_values = BufferBuilder::<u8>::new(
let mut output_values = Vec::with_capacity(
data_values
.iter()
.zip(offsets.iter_mut())
.map(|(data, offset)| data.len() - offset.peek().unwrap().as_usize())
.sum(),
);

let mut output_offsets = BufferBuilder::<Offset>::new(size + 1);
output_offsets.append(Offset::zero());
let mut output_offsets = Vec::with_capacity(size + 1);
output_offsets.push(Offset::zero());
for _ in 0..size {
data_values
.iter()
.zip(offsets.iter_mut())
.for_each(|(values, offset)| {
let index_start = offset.next().unwrap().as_usize();
let index_end = offset.peek().unwrap().as_usize();
output_values.append_slice(&values[index_start..index_end]);
output_values.extend_from_slice(&values[index_start..index_end]);
});
output_offsets.append(Offset::from_usize(output_values.len()).unwrap());
output_offsets.push(Offset::from_usize(output_values.len()).unwrap());
}

let builder = ArrayDataBuilder::new(GenericStringArray::<Offset>::DATA_TYPE)
.len(size)
.add_buffer(output_offsets.finish())
.add_buffer(output_values.finish())
.add_buffer(output_offsets.into())
.add_buffer(output_values.into())
.nulls(nulls);

// SAFETY - offsets valid by construction
Expand Down
Loading